Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3961 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2794. Min Act: -0.0001

Data Index: 260157 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2093. Min Act: -0.0001

Data Index: 515621 (C4 (Web Text))

Max Activating Token Index: 799

Text #2

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2394. Min Act: -0.0001

Data Index: 1404549 (Python Code)

Max Activating Token Index: 797

Text #3

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2456. Min Act: -0.0000

Data Index: 748053 (C4 (Web Text))

Max Activating Token Index: 374

Text #4

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2349. Min Act: -0.0000

Data Index: 587254 (C4 (Web Text))

Max Activating Token Index: 605

Text #5

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2273. Min Act: -0.0001

Data Index: 853531 (C4 (Web Text))

Max Activating Token Index: 232

Text #6

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2579. Min Act: -0.0001

Data Index: 1074153 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2143. Min Act: -0.0001

Data Index: 895494 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2133. Min Act: -0.0001

Data Index: 1615907 (Python Code)

Max Activating Token Index: 314

Text #9

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2272. Min Act: -0.0000

Data Index: 813864 (C4 (Web Text))

Max Activating Token Index: 699

Text #10

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2248. Min Act: -0.0001

Data Index: 1367530 (Python Code)

Max Activating Token Index: 432

Text #11

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2166. Min Act: -0.0000

Data Index: 1240063 (C4 (Web Text))

Max Activating Token Index: 861

Text #12

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2148. Min Act: -0.0001

Data Index: 352130 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2141. Min Act: -0.0000

Data Index: 515854 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2159. Min Act: -0.0001

Data Index: 1616926 (Python Code)

Max Activating Token Index: 188

Text #15

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2035. Min Act: -0.0001

Data Index: 75966 (C4 (Web Text))

Max Activating Token Index: 714

Text #16

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2101. Min Act: -0.0001

Data Index: 413886 (C4 (Web Text))

Max Activating Token Index: 1015

Text #17

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.1961. Min Act: -0.0001

Data Index: 1441219 (Python Code)

Max Activating Token Index: 135

Text #18

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2091. Min Act: -0.0001

Data Index: 440342 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2005. Min Act: -0.0000

Data Index: 247823 (C4 (Web Text))

Max Activating Token Index: 498